Claude Opus 5 (Adaptive Reasoning, High Effort): benchmark results
Provider: Anthropic. Released 2026-07-24. Access: API.
Unified ELO 1720 ± 1, rank #63 of 1761 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Science, Engineering & Mathematics | 56.21 | Accuracy (%) | 98.6 |
| Artificial Analysis Intelligence Index | 52.03 | Intelligence Index | 98.4 |
| AA Humanity's Last Exam | 52.83 | Accuracy (%) | 98.3 |
| AA Omniscience - Business | 50.7 | Accuracy (%) | 98.2 |
| AA GPQA Diamond | 93.74 | Accuracy (%) | 98 |
| AA Omniscience | 33.72 | Score | 97.5 |
| AA Omniscience - Health | 51.76 | Accuracy (%) | 97.3 |
| AA-Omniscience Accuracy | 58.88 | Accuracy (%) | 97.3 |
| AA CritPt | 28.29 | Accuracy (%) | 96.9 |
| AA Omniscience - Humanities & Social Sciences | 56 | Accuracy (%) | 96.5 |
| AA Omniscience - Software Engineering (SWE) | 83.9 | Accuracy (%) | 96.5 |
| AA Omniscience - Law | 55.2 | Accuracy (%) | 94.7 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5-adaptive-reasoning-high-effort · How It Works · Data refreshed daily, snapshot 2026-09-05.